From 88dccb4aa31c6c0b24bdd02b2b04cc424c9d450d Mon Sep 17 00:00:00 2001
From: guynachshon <guychuk@users.noreply.huggingface.co>
Date: Sun, 23 Feb 2025 12:37:06 +0000
Subject: [PATCH] Adding ONNX file of this model
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Beep boop I am the [ONNX export bot 🤖🏎️](https://huggingface.co/spaces/onnx/export). On behalf of [guychuk](https://huggingface.co/guychuk), I would like to add to this repository the model converted to ONNX.

What is ONNX? It stands for "Open Neural Network Exchange", and is the most commonly used open standard for machine learning interoperability. You can find out more at [onnx.ai](https://onnx.ai/)!

The exported ONNX model can be then be consumed by various backends as TensorRT or TVM, or simply be used in a few lines with 🤗 Optimum through ONNX Runtime, check out how [here](https://huggingface.co/docs/optimum/main/en/onnxruntime/usage_guides/models)!
---
 onnx/config.json            | 47 +++++++++++++++++++++++++++++++++++++
 onnx/generation_config.json |  6 +++++
 onnx/model.onnx             |  3 +++
 3 files changed, 56 insertions(+)
 create mode 100644 onnx/config.json
 create mode 100644 onnx/generation_config.json
 create mode 100644 onnx/model.onnx

diff --git a/onnx/config.json b/onnx/config.json
new file mode 100644
index 0000000..f04bdc1
--- /dev/null
+++ b/onnx/config.json
@@ -0,0 +1,47 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "onnx/distilbert/distilgpt2",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}
diff --git a/onnx/generation_config.json b/onnx/generation_config.json
new file mode 100644
index 0000000..bd968f4
--- /dev/null
+++ b/onnx/generation_config.json
@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.49.0"
+}
diff --git a/onnx/model.onnx b/onnx/model.onnx
new file mode 100644
index 0000000..20180f2
--- /dev/null
+++ b/onnx/model.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d24bf72a519e96e5cc81478e46eabe456a808426175c5b816c85c9c150ab031
+size 327855549